Hacker News Reader

Comment by siscia | Hacker News Reader

I may be completely wrong here but I would like to hear some one else opinion.

The speed of packets in fiber is exactly the one calculate doing the math combining together the speed of light and the refraction coefficient of fiber.

What slowndown everything is reaching an hub, detect the light and trasmute those impulses into bits, decide where to redirect the packet, and re-trasmute the bits into light impulse.

It is not the light domain the one that dominate the speed of packets but is the electronic domain.

Am I wrong?

View on HN

I submit as counter evidence the masts that high frequency traders want to build in Kent, UK. I believe the point is that they can replace some of the fibre in the link between London and Frankfurt with radio, which has a higher speed of light.

http://uk.businessinsider.com/plans-for-high-frequency-tradi...

I also reckon that a modern router can forward a packet in a microsecond. Once you don't involve software in the data plane, routing a packet should only take a few clock cycles.

Radio takes less time because it takes a direct, straight path from point to point. An optic fiber will always have a longer path.

And that's correct... inside the optic fiber, the light doesn't go straight in the core of the fiber. It bounces and is reflected, making the path longer.

Only in multimode fiber. Not so in single mode fiber. All subsea cables use singlemode fiber.

Radio waves in the atmosphere also travel faster than light in a fibre.

> which has a higher speed of light

What? How'd that be possible?

Light can travel in air much faster it can travel in glass.

Similarly, copper is faster than glass too (but not faster than air). The trade folks refer to copper in terms of "velocity factor". Example, some arbitrary RG-6 I'm looking at has a velocity factor of 81%. Equivalent refractive index is 1/.81 for ~ 1.23.

Refraction index of light in fiber is ~1.44. Rule of thumb for packets in transit is 200km/ms.

Light takes a millisecond to go 300km in air (it will only travel about 200 km in a fiber in that time), at long distances that time will dominate.

An example: http://oklo.org/2015/01/01/lightspeed/

You have 3 components that can be comparable with each other or not depending on many conditions:

- travel time on fiber

- transceiver conversion time

- time spent sitting in some buffer. This can dwarf other components on "common" networks!

http://www.m2optics.com/blog/bid/70587/Calculating-Optical-F...

Here is a suspicion I have, can someone who has experience in the field shed some light on this?:

In addition to the refraction index, you’d expect fibre optics to have another limiting factor: scatter. As light bounces off the side of the fibre, it gets scattered back and forth. I.o.w.: you’d expect a single, “perfect” pulse to eventually reach the other end as a slightly drawn out pulse (with its intensity spread out over a bell curve?). Is that true? If so, does that mean that in fibre optics , the longer the cable, the lower the frequency at which you can send pulses, to avoid “bleeding” from one into the next? And is it true radio doesn’t have that?

Or does fibre not work that way?

This is the case in Multimode fiber, which is used for short distances (meters). For anything longer, single mode fiber is used and the core of the fiber guides the light. See https://garyherlache.wikispaces.com/Digital+Communications+F...

Single mode fiber isn't immune to dispersion or other impairments, it just does better than multimode.

That looks like single mode fiber never refracts… Surely it can't go round any bend, then, though? (And I'm probably missing something obvious. It's been a while since I've done optics of any sort.)

> That looks like single mode fiber never refracts…

No, it does.

> Surely it can't go round any bend, then, though?

No, if you bend the fiber too much the light leaks out into the cladding.

I believe the fiber acts as a waveguide, essentially keeping the wavefront perpendicular to the fiber at all times.

Good overview below:

https://youtu.be/_KFpXuHqHQg

https://www.nanog.org/sites/default/files/Steenbergen.Everyt...

> In addition to the refraction index, you’d expect fibre optics to have another limiting factor: scatter.

Fiber optics have lots of limiting factors: power limits, chromatic and polarization mode dispersion, spectral attenuation, manufacturing imperfections, crosstalk, ...

Fiber optics are just better than a lot of other mediums, but that does not mean there aren't limitations.

The switch/router latency should be a couple of microseconds per “hub”.

I think you are right, there is no way you can slowdown light inside the fiber :-) So for sure everything we see as added latency compared to the baseline of traveling the cable distance must be something else, like software or other hardware.

Light is slower in a fiber, the refractive coefficient is pretty big, almost 1.5.

Yes, but the math was done in the speed of light inside the fiber, so any additional time you find in the RTT, must be software/hardware, or that you under-estimated length of the path.

Reply on news.ycombinator.com